Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network

This study proposes a unit module-based acceleration method for 2-D topology optimization. For the purpose, the first-stage topology optimization is performed until the predefined iteration. After a whole design domain is divided into a set of unit modules, information on the spatiotemporal characte...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Younghwan Joo, Yonggyun Yu, In Gwun Jang
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Convergence acceleration deep learning finite element method structural topology optimization Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/a7a0e20009334b0b86edc30479c5fb6e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a7a0e20009334b0b86edc30479c5fb6e
record_format	dspace
spelling	oai:doaj.org-article:a7a0e20009334b0b86edc30479c5fb6e2021-11-18T00:01:33ZUnit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network2169-353610.1109/ACCESS.2021.3125014https://doaj.org/article/a7a0e20009334b0b86edc30479c5fb6e2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9599692/https://doaj.org/toc/2169-3536This study proposes a unit module-based acceleration method for 2-D topology optimization. For the purpose, the first-stage topology optimization is performed until the predefined iteration. After a whole design domain is divided into a set of unit modules, information on the spatiotemporal characteristics of intermediate designs and a filtering radius is used to separately predict a near-optimal design of each unit module through a trained long short-term memory (convLSTM) network. Then, in the second-stage topology optimization, a combined near-optimal design of a whole design domain is used as an initial design to determine the optimized design in a more efficient way. To train a convLSTM network, a history of intermediate designs is obtained under a randomly generated boundary condition of a unit module. The filtering radius is also used as the training data to reflect the geometric features affected by a filtering process. For four examples with different design domains and boundary conditions, the proposed method successfully provides the accelerated convergence up to 6.09 with a negligible loss of accuracy less than 1.12% error. These numerical results also demonstrate that the proposed unit module-based approach achieves a scalable convergence acceleration at a design domain of an arbitrary size (or resolution).Younghwan JooYonggyun YuIn Gwun JangIEEEarticleConvergence accelerationdeep learningfinite element methodstructural topology optimizationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149766-149779 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Convergence acceleration deep learning finite element method structural topology optimization Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Convergence acceleration deep learning finite element method structural topology optimization Electrical engineering. Electronics. Nuclear engineering TK1-9971 Younghwan Joo Yonggyun Yu In Gwun Jang Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network
description	This study proposes a unit module-based acceleration method for 2-D topology optimization. For the purpose, the first-stage topology optimization is performed until the predefined iteration. After a whole design domain is divided into a set of unit modules, information on the spatiotemporal characteristics of intermediate designs and a filtering radius is used to separately predict a near-optimal design of each unit module through a trained long short-term memory (convLSTM) network. Then, in the second-stage topology optimization, a combined near-optimal design of a whole design domain is used as an initial design to determine the optimized design in a more efficient way. To train a convLSTM network, a history of intermediate designs is obtained under a randomly generated boundary condition of a unit module. The filtering radius is also used as the training data to reflect the geometric features affected by a filtering process. For four examples with different design domains and boundary conditions, the proposed method successfully provides the accelerated convergence up to 6.09 with a negligible loss of accuracy less than 1.12% error. These numerical results also demonstrate that the proposed unit module-based approach achieves a scalable convergence acceleration at a design domain of an arbitrary size (or resolution).
format	article
author	Younghwan Joo Yonggyun Yu In Gwun Jang
author_facet	Younghwan Joo Yonggyun Yu In Gwun Jang
author_sort	Younghwan Joo
title	Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network
title_short	Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network
title_full	Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network
title_fullStr	Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network
title_full_unstemmed	Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network
title_sort	unit module-based convergence acceleration for topology optimization using the spatiotemporal deep neural network
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/a7a0e20009334b0b86edc30479c5fb6e
work_keys_str_mv	AT younghwanjoo unitmodulebasedconvergenceaccelerationfortopologyoptimizationusingthespatiotemporaldeepneuralnetwork AT yonggyunyu unitmodulebasedconvergenceaccelerationfortopologyoptimizationusingthespatiotemporaldeepneuralnetwork AT ingwunjang unitmodulebasedconvergenceaccelerationfortopologyoptimizationusingthespatiotemporaldeepneuralnetwork
_version_	1718425243535540224

Unit Module-Based Convergence Acceleration for Topology Optimization Using the Spatiotemporal Deep Neural Network

Ejemplares similares